© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25624
    Prev
    Next
    INDEX
    Explanations

    code entities or formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Matériel
    -1.07
     podí
    -0.88
     chẳng
    -0.88
    包裝
    -0.87
    ızı
    -0.87
    ulado
    -0.85
     setState
    -0.84
     personnages
    -0.82
    澳大利
    -0.82
     CAROL
    -0.81
    POSITIVE LOGITS
     NEED
    0.83
     JO
    0.81
    }\
    0.81
     Eur
    0.80
     Consumer
    0.80
     however
    0.79
     difer
    0.78
     прием
    0.78
    震惊
    0.77
     NOTE
    0.76
    Activations Density 0.213%

    No Known Activations